Fault Diagnosis Method of Transformer Core Looseness Based on ICEEMDAN-RCMDEand K-means

ZE Hengpeng; MA Hongzhong; WAN Keli; NI Yiming; XUE Jiantong

doi:10.13296/j.1001-1609.hva.2026.06.007

您当前的位置：

首页 >

文章列表页 >

Fault Diagnosis Method of Transformer Core Looseness Based on ICEEMDAN-RCMDEand K-means

Research & Analysis | 更新时间：2026-06-10

- Fault Diagnosis Method of Transformer Core Looseness Based on ICEEMDAN-RCMDEand K-means
- High Voltage Apparatus Vol. 62, Issue 6, Pages: 59-69(2026)
- 作者机构：
  
  河海大学能源与电气学院，南京 211100
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2026.06.007
  CLC：
- Received：08 September 2025，
  
  Revised：2025-12-01，
  
  Published：16 June 2026
- 稿件说明：
移动端阅览
ZE Hengpeng, MA Hongzhong, WAN Keli, et al. Fault Diagnosis Method of Transformer Core Looseness Based on ICEEMDAN-RCMDEand K-means[J]. High Voltage Apparatus, 2026, 62(6): 59-69.
DOI：

ZE Hengpeng, MA Hongzhong, WAN Keli, et al. Fault Diagnosis Method of Transformer Core Looseness Based on ICEEMDAN-RCMDEand K-means[J]. High Voltage Apparatus, 2026, 62(6): 59-69. DOI： 10.13296/j.1001-1609.hva.2026.06.007.

摘要

为了更加有效地对变压器铁心松动故障进行诊断，针对变压器带载运行时的振动信号，提出了一种基于改进的完全噪声辅助聚合经验模态分解（ICEEMDAN）算法和精细复合多尺度散布熵（RCMDE）的变压器铁心松动故障诊断方法。首先采用ICEEMDAN算法对变压器铁心在不同松动程度下的振动信号序列进行分解，之后通过RCMDE和主成分分析法（PCA）计算特征量的熵值并实行降维，最后采用K-means聚类算法对多组低维特征值矩阵表示的振动数据进行故障的分类识别。结合某10 kV变压器的铁心松动故障模拟实验，结果表明，相较于传统的模态分解和特征值提取算法，所提基于ICEEMDAN-RCMDE的K-means聚类效果优异，准确率达95.6%，能有效识别变压器铁心松动故障。

Abstract

To doagnose transformer core looseness faults more effectively

a fault diagnosis method based on the improved complete ensembleEMD (ICEEMDAN) algorithm and the refined composite multiscale dispersion entropy (RCMDE) is proposed for the vibration signals of the transformer under load operation. First

the ICEEMDAN algorithm is used to decompose the vibration signal sequence of the transformer core under different degrees of looseness.Then

the entropy value of the eigenvalues is calculated by using RCMDE and Principal Component Analysis (PCA) and dimensionality reduction is carried out. Finally

the K-means clustering algorithm is used to classify and identify faults on the vibration data represented by multi-groups of low-dimensional eigenvalue matrices. Combined with the core looseness fault simulation experiment of a 10 kV transformer

the results show that

compared with traditional modal decomposition and eigenvalue extraction algorithms

the proposed K-means clustering based on ICEEMDAN-RCMDEachieves excellent clustering performance with an accuracy rate of 95.6% and can effectively identify transformer core loosenese faults.

关键词

Keywords

references

马宏忠,赵宏飞,陈楷,等.基于振动的变压器铁芯松动判定方法[J].电力系统自动化,2013,37(14):101-106.

MA Hongzhong, ZHAO Hongfei, CHEN Kai, et al.Determine method for transformer core looseness based on vibration[J]. Automation of Electric Power Systems,2013,37(14):101-106.

周广宇,桑旺,陈启辉,等.新能效电力变压器铁心结构优化的思考及应用[J].变压器,2025,62(9):19-24.

ZHOU Guangyu, SANG Wang, CHEN Qihui, et al.Considerations and applications of core structure optimization in new energyefficiency power transformers[J]. Transformer,2025,62(9):19-24.

刘道生,刘龙生,王永胜,等.非晶合金立体卷铁心振动特性分析及其振动抑制[J].变压器,2025,62(6):1-8.

LIU Daosheng, LIU Longsheng, WANG Yongsheng, et al.Analysis of vibration characteristics of amorphous alloy three-dimensional coiled core and its suppression method[J]. Transformer,2025,62 (6):1-8.

王然丰.电力变压器铁心振动模态分析[J].变压器,2024,61(10):41-45.

WANG Ranfeng.Vibration modal analysis of power transformer core[J]. Transformer,2024,61(10):41-45.

徐春苗,于健,蔡铭.硅钢片干式铁心电抗器的电磁—机械耦合振动特性研究[J].变压器,2025,62(8):39-44.

XU Chunmiao, YU Jian, CAI Ming.Electromagnetic-mechanical coupling cibration characteristics of dry core reactor with silicon steel sheet[J]. Transformer,2025,62(8):39-44.

黄丰,郭淳,邱冰兵,等.基于电磁—结构场的油浸式变压器振动特性及信号反演研究[J].电力科学与技术学报,2025,40 (2):276-286.

HUANG Feng, GUO Chun, QIU Bingbing, et al.Vibration characteristics and signal inversion of oil-immersed transformer based on electromagnetic-structural field[J]. Journal of Electric Power Science and Technology,2025,40(2):276-286.

赵莉华,张振东,张建功,等.运行工况波动下基于振动信号的变压器故障诊断方法[J].高电压技术,2020,46(11):3925-3933.

ZHAO Lihua, ZHANG Zhendong, ZHANG Jiangong, et al.Diagnosis methods for transformer faults based on vibration signal under fluctuating operating conditions[J]. High Voltage Engineering, 2020,46(11):3925-3933.

刘胜军,孙志鹏,沈辰,等.基于振动频谱分析和总谐波畸变率的电力变压器故障诊断方法研究[J].电网与清洁能源, 2021,37(3):86-91.

LIU Shengjun, SUN Zhipeng, SHEN Chen, et al.Research on fault diagnosis of power transformers based on spectral analysis of vibration signals and total harmonic distortion[J]. Power System and Clean Energy,2021,37(3):86-91.

赵莉华,程胤璋,武立平,等.基于模态分析的变压器铁芯故障诊断[J].电测与仪表,2019,56(11):8-13.

ZHAO Lihua, CHENG Yinzhang, WU Liping, et al.Transformer core fault diagnosis based on modal analysis[J]. Electrical Measurement & Instrumentation,2019,56(11):8-13.

赵莉华,丰遥,谢荣斌,等.基于振动信号分形维数的变压器松动诊断方法[J].电测与仪表,2018,55(3):7-12.

ZHAO Lihua, FENG Yao, XIE Rongbin, et al.Transformer fault diagnosis method based on fractal dimension of vibration signals[J]. Electrical Measurement & Instrumentation,2018,55(3):7-12.

张大海,杨宇辰,刘艳梅,等.基于EMD与Spearman相关系数的混合直流线路纵联保护方法[J].电力系统保护与控制, 2021,49(9):1-11.

ZHANG Dahai, YANG Yuchen, LIU Yanmei, et al.Hybrid HVDC line pilot protection method based on EMD and Spearman correlation coefficient[J]. Power System Protection and Control, 2021,49(9):1-11.

HUANG N E, SHEN Z, LONG S R, et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and nonstationary time series analysis[J]. Proceedings of the Royal Society, 1998,454(1971):903-995.

TORRES M E, COLOMINAS M A, SCHLOTTHAUER G, et al.A complete ensemble empirical mode decomposition with adaptive noise[C]//2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).Prague, Czech Republic:IEEE,2011:4144-4147.

罗兵,徐立,王婷婷,等.基于CEEMDAN-GAF的变压器机械故障检测方法[J].电测与仪表,2024,61(7):169-176.

LUO Bing, XU Li, WANG Tingting, et al.Mechanical faults detection method for transformers based onCEEMDAN-GAF[J]. Electrical Measurement & Instrumentation,2024,61(7):169-176.

杨洋,郭兴明,郑伊能,等.基于ICEEMDAN-MSE的左室舒张功能障碍心音信号的识别研究[J].仪器仪表学报,2022,43 (1):274-281.

YANG Yang, GUO Xingming, ZHENG Yineng, et al.Study on left ventricular diastolic dysfunction heart sound signals identification based onICEEMDAN - MSE[J]. Chinese Journal of Scientific Instrument,2022,43(1):274-281.

王浩楠,崔宝珍,彭智慧,等.应用ICEEMDAN和SVM的行星齿轮箱故障诊断[J].机械科学与技术,2023,42(1):24-30.

WANG Haonan, CUI Baozhen, PENG Zhihui, et al.Fault diagnosis of planetary gearbox usingICEEMDANand SVM[J]. Mechanical Science and Technology for Aerospace Engineering,2023,42(1):24-30.

ROSTAGHI M, AZAMI H.Dispersion entropy:A measure for timeseries analysis[J]. IEEE Signal Processing Letters,2016,23(5):610-614.

骆钊,张涛,阮彦俊,等.基于APSO-SSD-SVD的特高压换流站OLTC振动信号降噪方法[J].电力系统保护与控制,2024,52 (21):13-23.

LUO Zhao, ZHANG Tao, RUAN Yanjun, et al.Noise reduction method for the OLTC vibration signal of a UHV converter station based onAPSO - SSD - SVD[J]. Power System Protection and Control,2024,52(21):13-23.

COSTA M, GOLDBERGER A L, PENG C K.Multiscale entropy analysis of biological signals[J]. Physical Review E Statistical Nonlinear and Soft Matter Physics,2005,71(2 Pt 1):021906.

程珩,励文艳,权龙,等.基于VMD-MDE和ELM的柱塞泵微弱故障诊断[J].振动、测试与诊断,2020,40(4):635-642.

CHENG Hang, LI Wenyan, QUAN Long, et al.Weak fault diagnosis of piston pump based on VMD-MDE and ELM[J]. Journal of Vibration, Measurement & Diagnosis,2020,40(4):635-642.

AZAMI H, ROSTAGHI M, ABASOLO D, et al.Refined composite multiscale dispersion entropy and its application to biomedical signals[J]. IEEE Transactions on Biomedical Engineering,2017,64 (12):2872-2879.

韩国国,史小军,王晖,等.基于RCMDE和KFCM的煤矿电网故障选线方法[J].工矿自动化,2022,48(8):92-99.

HAN Guoguo, SHI Xiaojun, WANG Hui, et al.Fault line selection method for coal mine power grid based on RCMDE and KFCM[J]. Industry and Mine Automation,2022,48(8):92-99.

颜湘武,李君岩.基于主成分分析法的直驱式风电场分群方法[J].电力系统保护与控制,2020,48(5):127-133.

YAN Xiangwu, LI Junyan.Grouping method of direct drive wind farm based on principal component analysis[J]. Power System Protection and Control,2020,48(5):127-133.

韩平平,夏雨,丁明,等.基于PCA和CA-ST方法的风电场等值建模研究[J].太阳能学报,2020,41(11):267-277.

HAN Pingping, XIA Yu, DING Ming, et al. Equivalent modeling of wind farm based on PCA and CA-ST methods[J]. Acta Energiae Solaris Sinica,2020,41(11):267-277.

杨金东,李文.基于K-Means算法的配电网负荷和拓扑等效方法[J].电力电容器与无功补偿,2022,43(2):147-153.

YANG Jindong, LI Wen.Equivalent method of distribution network load and topology based on K-Means algorithm[J]. Power Capacitor& Reactive Power Compensation,2022,43(2):147-153.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application of Neural Network Based on Improved Particle Swarm Optimization in the Condition Monitoring of Transformer

Improved Mechanical Fault Diagnosis Technology of Transformer Based on Similarity of Vibration Signal Characteristic Matrix

Vibration Signal Diagnosis Method of Transformer Winding Looseness Defect Based on VMD and Optimized SVM

Transformer Fault Diagnosis Method Based on KELM Optimized by Improved Sparrow Search Algorithm

Review of Research on the Short Circuit Withstand Capability of Transformer

Related Author

JIA Rong1

LI Hong-bin2

KANG Hui-xi2

HONG Gang1

WU Liping

YANG Liu

LI Gang

JIA Zhiyi

Related Institution

Department of Electrical Engineering,Xi′an University of Technology,Xi′an

Gansu Tou River Hydropower Development Ltd.

State Grid Shanxi Yangquan Power Supply Company

Sichuan University

State Grid Jiangsu Electric Power Company Nanjing Power Supply Company

⁰